Labs

Datum	Č.T.	S/L	Náplň	Učitel	Materiály
25-26.09.2023	1	L	Intro: Introduction to the course, Python, NumPy, GitHub, Jupyter Notebook and the environment.	PV	Python & Numpy Notebook Notebook (Zip)
02-03.10.2023	2	S	1D regression and 2D classification: Revision of the regression and classification theory, analytic gradient computation, gradient in computational graph and loss minimization.	KZ	template_for_students.zip labs_02_regression.pdf
09-10.10.2023	3	L	Autograd: Computational graphs, backpropagation and the automatic gradient computation.	JV	HW1: Autograd engine_lab engine_ref lab03.pdf
16-17.10.2023	4	S	Classification I - Intro: Revision of the classification theory, KNN and the linear classifier.	AK
23-24.10.2023	5	L	Classification II - NN: Classification using neural networks.	AK	HW2: Classification
30-31.10.2023	6	S	CNN I - Intro: Introduction to the convolution and to the PyTorch library.	JV	lab06.zip lab06_ref.zip
06-07.11.2023	7	L	Optimization: Convergence rate, oscillations, diminishing gradients.	KZ	optimizers_student_template.py.zip
13-14.11.2023	8	S	CNN II: Training a classifier: Training a simple CNN classifier.	JV	lab08.zip lab08_ref.zip
20-21.11.2023	9	L	Dean's day
27-28.11.2023	10	S	CNN III - Semantic segmentation: Segmentation of images using CNN.	PV	HW 3 - Segmentation HW3
04-05.12.2023	11	L	RL I Intro:Introduction to the reinforcement learning. Policy gradient.	TT	HW4: Reinforcement learning
11-12.12.2023	12	S	RL II - Deep learning:Deep reinforcement learning.	TT
18-19.12.2023	13	L	CNN IV - Semantic Segmentation: Presentations, Team projects	PV
08-09.01.2023	14	S	Transformers: Applications of the transformers.	DC	lab05.zip